Embedded AI Engineer

Qualifications

• Deep knowledge of Python programming language

• Experience with PyTorch, OpenCV, and Tensorflow for deep learning

• Familiarity with distributed data pipelines using Beam/Spark/WebDataset

• Experience designing scalable server-side systems using NodeJS or Golang

• Understanding of DevOps and infrastructure management using Docker, Kubernetes, and GPU scheduling

• About You

• You should be comfortable working in a fast-paced environment, learning new skills daily, and contributing to a small but collaborative team

Responsibilities

• As an Embedded AI Engineer, you'll be responsible for distilling and pruning AI models for on-device deployment, leveraging expertise in computer vision and deep learning architectures

• Design and implement efficient AI model distillation techniques for on-device deployment

• Develop and optimize pruning strategies for AI models to reduce computational overhead

• Collaborate with cross-functional teams to integrate AI models into existing systems

• Stay up-to-date with the latest advancements in AI, computer vision, and deep learning architectures

Full Description

Job Title:

Embedded AI Engineer (CV Model Distillation & Pruning)

About Us

We are a pioneering startup at the forefront of spatial AI, dedicated to solving autonomy universally.

Our team innovates at the foundational layer of AI by training our own AI models.

Our Team

We comprise AI leaders from Google X, Google Brain, and Unity.

Our founders have deep commercialization insights across multipleenterprise segments, and we enjoy long, in-depth discussions on unexplored AI use cases in autonomy.

Your Role

We're seeking individuals with an innate curiosity for intellectual pursuits, a passion for learning new things quickly, and a track record of solving complex problems with creative solutions.

As an Embedded AI Engineer, you'll be responsible for distilling and pruning AI models for on-device deployment, leveraging expertise in computer vision and deep learning architectures.

Key Responsibilities

• Design and implement efficient AI model distillation techniques for on-device deployment.

• Develop and optimize pruning strategies for AI models to reduce computational overhead.

• Collaborate with cross-functional teams to integrate AI models into existing systems.

• Stay up-to-date with the latest advancements in AI, computer vision, and deep learning architectures.

Requirements

• Deep knowledge of Python programming language.

• Experience with PyTorch, OpenCV, and Tensorflow for deep learning.

• Familiarity with distributed data pipelines using Beam/Spark/WebDataset.

• Experience designing scalable server-side systems using NodeJS or Golang.

• Understanding of DevOps and infrastructure management using Docker, Kubernetes, and GPU scheduling.

Preferred Qualifications

• Experience with robotics and spatial data analytics.

• Familiarity with geographic information systems and spatial databases (PostGIS).

• Knowledge of Git and experience collaborating with teams on GitHub or GitLab.

About You

You should be comfortable working in a fast-paced environment, learning new skills daily, and contributing to a small but collaborative team. If you're passionate about AI, innovation, and problem-solving, we'd love to hear from you.